{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DDKUGPHAVFNYUSTSJOBV4S6TYA","short_pith_number":"pith:DDKUGPHA","schema_version":"1.0","canonical_sha256":"18d5433ce0a95b8a4a724b835e4bd3c016874a6d7c454fdf3ee8377b6e9efdf8","source":{"kind":"arxiv","id":"1904.03597","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbo Jiao, Jiangliu Wang, Linchao Bao, Shengfeng He, Wei Liu, Yunhui Liu","submitted_at":"2019-04-07T07:27:37Z","abstract_excerpt":"We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a frame-by-frame basis, which are not applicable to many video analytic tasks where spatio-temporal features are prevailing. In this paper we propose a novel self-supervised approach to learn spatio-temporal features for video representation. Inspired by the success of two-stream approaches in video classification, we propose to learn visual features by regressing both mot"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1904.03597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T07:27:37Z","cross_cats_sorted":[],"title_canon_sha256":"2cc4ec3c0c5f52778838cbb4eaa0131fa7d2a98232003ef9b84999a94c99fed0","abstract_canon_sha256":"d051abaceccc9de2271c63332f0e97d2134d5d7a1e2d59bffcc96ebf96b95acd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:12.860585Z","signature_b64":"smUadI57Oz3bfQXrduDMGPOfOMdLHBooAcDBW6U+1POXHJ0n/F3/tg+kB9LLGksPKq3lrazyAn7j44/zbbRGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18d5433ce0a95b8a4a724b835e4bd3c016874a6d7c454fdf3ee8377b6e9efdf8","last_reissued_at":"2026-05-17T23:49:12.859944Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:12.859944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbo Jiao, Jiangliu Wang, Linchao Bao, Shengfeng He, Wei Liu, Yunhui Liu","submitted_at":"2019-04-07T07:27:37Z","abstract_excerpt":"We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a frame-by-frame basis, which are not applicable to many video analytic tasks where spatio-temporal features are prevailing. In this paper we propose a novel self-supervised approach to learn spatio-temporal features for video representation. Inspired by the success of two-stream approaches in video classification, we propose to learn visual features by regressing both mot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03597","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.03597","created_at":"2026-05-17T23:49:12.860060+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03597v1","created_at":"2026-05-17T23:49:12.860060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03597","created_at":"2026-05-17T23:49:12.860060+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDKUGPHAVFNY","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDKUGPHAVFNYUSTS","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDKUGPHA","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA","json":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA.json","graph_json":"https://pith.science/api/pith-number/DDKUGPHAVFNYUSTSJOBV4S6TYA/graph.json","events_json":"https://pith.science/api/pith-number/DDKUGPHAVFNYUSTSJOBV4S6TYA/events.json","paper":"https://pith.science/paper/DDKUGPHA"},"agent_actions":{"view_html":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA","download_json":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA.json","view_paper":"https://pith.science/paper/DDKUGPHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03597&json=true","fetch_graph":"https://pith.science/api/pith-number/DDKUGPHAVFNYUSTSJOBV4S6TYA/graph.json","fetch_events":"https://pith.science/api/pith-number/DDKUGPHAVFNYUSTSJOBV4S6TYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/action/storage_attestation","attest_author":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/action/author_attestation","sign_citation":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/action/citation_signature","submit_replication":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/action/replication_record"}},"created_at":"2026-05-17T23:49:12.860060+00:00","updated_at":"2026-05-17T23:49:12.860060+00:00"}